Systems to monitor characteristics of materials involving optical and acoustic techniques

Abstract

An example system for monitoring a characteristic of a material. The system includes a stimulator to provide a stimulus signal to the material. The stimulus signal includes at least one of an electrical signal, a magnetic signal, an optical signal, and an acoustic signal. The system includes a sensor to measure a response signal from the material. The response signal includes at least one of an electrical signal, a magnetic signal, an optical signal, and an acoustic signal. At least one of the stimulus signal and the response signal includes an optical signal or an acoustic signal. The system further includes a controller in communication with the stimulator and the sensor to apply machine learning to determine a characteristic of the material based on the stimulus signal and the response signal, wherein the characteristic is not directly measurable.

1 - 15 . (canceled) 
     
     
         16 . A device for monitoring a characteristic of a mammal, the device comprising:
 a toilet body for receiving biological waste from a mammal;   a seat connected to the toilet body for supporting the mammal, the seat comprising a mammal monitoring device for detecting when the mammal is interacting with the seat and to measure an attribute of the mammal, the mammal monitoring device is configured to contact the mammal, the mammal monitoring device comprising:
 a first stimulator to provide a first stimulus signal to the mammal, the first stimulus signal including at least one of a first electrical signal and a first optical signal; 
 a first sensor to measure a first response signal from the mammal, the first response signal including at least one of a first electrical response signal and a first optical response signal; and 
   a waste body to contain the biological waste from the mammal;   a waste monitoring device included in the waste body, the waste monitoring device comprising:
 a second stimulator to provide a second stimulus signal to the biological waste, the second stimulus signal including a magnetic signal, a second electrical signal, and a second optical signal; 
 a second sensor to measure a second response signal from the biological waste, the second response signal including a magnetic response signal, a second electrical response signal and a second optical response signal; 
   an integrated circuit electrically connected to the mammal monitoring device and the waste monitoring device, the integrated circuit comprising:
 a communications circuit to communicate the stimulus signals and the response signals via a network; and 
 a memory for storing the stimulus signals and response signals; and 
   a computing device for receiving the stimulus signals and the response signals via the network, the computing device comprising:
 a processor configured to receive the first stimulus signal and the first response signal from the mammal monitoring device, the processor configured to apply machine learning to determine a first characteristic of the mammal based on the first stimulus signal and first response signal, the machine learning applied via a first machine learning model trained with library data to recognize characteristics of the mammal relating to previously measured signals;
 wherein the processor is further configured to analyze the first stimulus signal and the first response signal using an electrical analytical methodology selected from a group consisting of: potentiometry, coulometry, voltammetry, impedance spectroscopy, square wave voltammetry, stair-case voltammetry, cyclic voltammetry, alternating current voltammetry, amperometry, pulsed amperometry, galvanometry, and polarography; 
 wherein, when the second signal related to the biological waste includes an electrical signal, the processor is further configured to analyze the second stimulus signal and the second response signal using an electrical analytical methodology selected from a group consisting of: potentiometry, coulometry, voltammetry, impedance spectroscopy, square wave voltammetry, stair-case voltammetry, cyclic voltammetry, alternating current voltammetry, amperometry, pulsed amperometry, galvanometry, and polarography;
 wherein the processor is further configured to analyze the second stimulus signal and the second response signal related to the biological waste using a magnetic stimulation analytical methodology, wherein the second response signal comprises at least one of a static magnetic signal and a dynamic magnetic signal, wherein when the second response signal comprises a dynamic magnetic signal, the dynamic magnetic signal is characterized as a one or more of: a sine wave, a square wave, a series of pulses, a complex signal repeating a pattern, and a complex signal that does not repeat; 
 
 wherein the processor is configured to apply machine learning to determine a characteristic of the biological waste based on the second stimulus signal and the second response signal, the machine learning applied via a second machine learning model trained with the library data to recognize characteristics of the biological waste relating to previously measured signals; 
 
 wherein the processor is further configured apply machine learning to determine a second characteristic of the mammal based on at least one of the determined characteristic of the biological waste and the determined first characteristic of the mammal, the machine learning applied via a third machine learning model trained with the library data to recognize characteristics of the mammal relating to previously determined characteristics of waste and mammals; and 
   a power source to power at least one of the following: the mammal monitoring device, the waste monitoring device, the communications circuit, and the processor.   
     
     
         17 . The device of  claim 16  wherein the machine learning uses one or more techniques selected from a group consisting of: neural network, support vector machine, random forest, convolutional neural network, deep learning, and deep belief network. 
     
     
         18 . The device of  claim 16  wherein the mammal is a human, and the processor is configured to determine a health characteristic of the human based on the characteristics of the biological waste and the characteristics of the human. 
     
     
         19 . The device of  claim 16  wherein the processor is configured to detect a pathogen in the biological waste. 
     
     
         20 . The device of  claim 19  wherein the pathogen is a bacterium. 
     
     
         21 . The device of  claim 19  wherein the pathogen is a coliform. 
     
     
         22 . The device of  claim 19  wherein the pathogen is an  Escherichia coli  bacterium. 
     
     
         23 . The device of  claim 16  wherein the processor is configured to detect a disease of the mammal. 
     
     
         24 . The device of  claim 23  wherein the disease is selected from a group consisting of: a urinary tract infection, elevated antigen levels, and a cancer. 
     
     
         25 . The device of  claim 16  wherein the processor is configured to detect a biological analyte. 
     
     
         26 . The device of  claim 25  wherein the biological analyte is a cancer-specific analyte. 
     
     
         27 . Use of the device of  claim 16  to monitor a medication taken by the mammal. 
     
     
         28 . The use of  claim 27  wherein monitoring the medication comprises monitoring a dosage of the medication. 
     
     
         29 . The use of  claim 27  wherein monitoring the medication is for titrating the medication. 
     
     
         30 . The use of  claim 27  wherein monitoring the medication is for determining an effectiveness of the medication. 
     
     
         31 . Use of the device of  claim 16  in diagnosing a patient and providing treatment for a disease condition detected by the processor. 
     
     
         32 . The device of  claim 16  wherein the power source includes one or more of: a wired power supply, a battery, a solar cell, an energy harvester. 
     
     
         33 . The device of  claim 16  wherein the second machine learning model is to determine a property that is a not directly measurable characteristic of the mammal, the second machine learning model trained with the library data to recognize the not directly measurable characteristic of the mammal, the library data relating the previously measured signals to a known not directly measurable characteristic of the mammal, the previously measured signals comprising electrical and optical signals. 
     
     
         34 . The device of  claim 16  wherein the second machine learning model is to determine a property that is a not directly measurable characteristic of the biological waste, the second machine learning model trained with the library data to recognize the not directly measurable characteristic of the biological waste, the library data relating previously measured signals to known not directly measurable characteristics of the biological waste, the previously measured signals comprising magnetic, optical and electrical signals. 
     
     
         35 . The device of  claim 16  wherein the waste monitoring device further comprises an acoustic transmitter to provide an acoustic stimulus to the biological waste, and an acoustic detector to measure at least one acoustic signal responsive to the acoustic stimulus and related to an acoustic property of the biological waste, and wherein the second machine learning model is further trained with the library data to determine a characteristic of the biological waste. 
     
     
         36 . The device of  claim 16  wherein the device is in communication with at least one or more of: a cloud computing platform, a mobile device, and a computer. 
     
     
         37 . A non-transitory machine-readable medium comprising instructions that when executed cause a processor to:
 obtain a first response signal measured by an mammal monitoring device in communication with the processor, the first response signal comprising a first electrical signal and a first optical signal from a mammal, the first response signal responsive to a first electrical stimulus and the first optical response signal responsive to a first optical stimulus;
 wherein the first response signal is measured using an electrical analytical methodology selected from a group consisting of: potentiometry, coulometry, voltammetry, impedance spectroscopy, square wave voltammetry, stair-case voltammetry, cyclic voltammetry, alternating current voltammetry, amperometry, pulsed amperometry, galvanometry, and polarography; 
   apply a first machine learning model to determine a first characteristic of a mammal interacting with a toilet based on the first response signal, the first machine learning model trained with library data to recognize one or more characteristics of the mammal, the library data relating previously measured signals to an electrical property, an optical property, or a magnetic property of the mammal;   obtain a second response signal measured by a waste monitoring device in communication with the processor, the second response signal comprising a second electrical signal, a second optical signal, and a magnetic signal from biological waste deposited by the mammal, the second response signal responsive to a second electrical stimulus, the second optical signal responsive to a second optical stimulus, and the magnetic signal responsive to a magnetic stimulus, the magnetic stimulus comprising at least one of a static signal and a dynamic signal and wherein, when the magnetic stimulus comprises a dynamic signal, the dynamic signal is selected from a group consisting of: a sine wave, a square wave, a series of pulses, or a complex signal of either repeating a pattern or a complex signal that does not repeat;
 wherein the second response signal is measured using an electrical analytical methodology selected from a group consisting of: potentiometry, coulometry, voltammetry, impedance spectroscopy, square wave voltammetry, stair-case voltammetry, cyclic voltammetry, alternating current voltammetry, amperometry, pulsed amperometry, galvanometry, and polarography; and 
   apply a second machine learning model to determine a characteristic of the biological waste based on the second response signal, the second machine learning model trained with library data to recognize one or more characteristics of the biological waste, the library data relating previously measured signals to an electrical property, optical property, or magnetic property of the biological waste; and   apply a third machine learning model to determine a second characteristic of the mammal based on at least one of the characteristic of the biological waste and the first characteristic of the mammal, the third machine learning model trained with the library data to recognize health characteristics of the mammal relating to previously determined health characteristics.   
     
     
         38 . The non-transitory machine-readable medium of  claim 37 , wherein the first machine learning model is to further determine a property that is a not directly measurable characteristic of the mammal, the first machine learning model trained with the library data to recognize the not directly measurable characteristic of the mammal, the library data relating previously measured signals to a known not directly measurable characteristics of the waste or mammal, the previously measured signals comprising electrical and optical signals. 
     
     
         39 . The non-transitory machine-readable medium of  claim 37 , wherein the second machine learning model is to determine a property that is a not directly measurable characteristic of the biological waste, the second machine learning model trained with the library data to recognize the not directly measurable characteristic of the biological waste, the library data relating previously measured signals to known not directly measurable characteristics of the waste or mammal, the previously measured signals comprising electrical, magnetic, and optical signals. 
     
     
         40 . The non-transitory machine-readable medium of  claim 37 , wherein the mammal is a human and wherein the instructions when executed further cause the processor to determine a health characteristic of the human. 
     
     
         41 . The non-transitory machine-readable medium of  claim 37 , wherein the instructions when executed further cause the processor to determine a nutritional health characteristic of the mammal. 
     
     
         42 . The non-transitory machine-readable medium of  claim 37 , wherein the instructions when executed further cause a machine learning algorithm to detect a cancer disease of the mammal. 
     
     
         43 . The non-transitory machine-readable medium of  claim 37 , wherein the instructions when executed further cause a machine learning algorithm to detect a pathogen infection of the mammal. 
     
     
         44 . A monitoring system for monitoring a characteristic a mammal, the monitoring system comprising:
 a toilet device comprising:
 a toilet body for receiving biological waste excreted from a mammal; 
 a seat connected to the toilet body for supporting the mammal, the seat comprising: an mammal monitoring device for detecting when the mammal is interacting with the seat, the mammal monitoring device positionable to contact the mammal, the mammal monitoring device comprising:
 a first stimulator to provide a first stimulus signal to the mammal, the first stimulus signal including at least one of an electrical signal and an optical signal; and 
 a first sensor to measure a first response signal from the mammal, the first response signal including at least one of an electrical signal and an optical signal; 
 
 a waste monitoring device included in the waste body and positionable to interact with the biological waste, the waste monitoring device comprising:
 a second stimulator to provide a second stimulus signal to the biological waste, the second stimulus signal including at least one of a static magnetic signal and a dynamic magnetic signal, wherein when the second stimulus signal comprises a dynamic magnetic stimulus, the second stimulus signal is characterized as a one or more of: a sine wave, a square wave, a series of pulses, or a complex signal of either repeating a pattern or a complex signal that does not repeat; and 
 a second sensor to measure a second response signal from the biological waste, the second response signal including a magnetic signal; and 
 the second stimulator and the second sensor are further configured to apply an electrical stimulus to the biological waste and measure an electrical signal from the biological waste, wherein an electrical analytical methodology is applied selected from a group consisting of: potentiometry, coulometry, voltammetry, impedance spectroscopy, square wave voltammetry, stair-case voltammetry, cyclic voltammetry, alternating current voltammetry, amperometry, pulsed amperometry, galvanometry, and polarography; and 
 the second stimulator and the second sensor are further configured to apply an optical stimulus to the biological waste and measure an optical signal; and 
 
 a communications circuit electrically connected to the mammal monitoring device and the waste monitoring device, the communications circuit to communicate the stimulus signals and the response signals via a network; and 
   a computing device comprising a processor, the processor configured to receive the stimulus signals and the response signals via the network and apply machine learning to determine a first characteristic of the mammal and a characteristic of the biological waste based on the stimulus signals and the response signals;
 wherein the processor is further configured to analyze the first stimulus signal and the first response signal where an electrical analytical methodology was applied to the first stimulator and first sensor electrical signals selected from a group consisting of: potentiometry, coulometry, voltammetry, impedance spectroscopy, square wave voltammetry, stair-case voltammetry, cyclic voltammetry, alternating current voltammetry, amperometry, pulsed amperometry, galvanometry, and polarography; 
 wherein the processor is further configured to analyze the second stimulus signal and the second response signal where a magnetic stimulation analytical methodology was applied to the second stimulator magnetic signals, and an electrical analytical methodology applied to the second stimulator and second sensor electrical signals selected from a group consisting of: potentiometry, coulometry, voltammetry, impedance spectroscopy, square wave voltammetry, stair-case voltammetry, cyclic voltammetry, alternating current voltammetry, amperometry, pulsed amperometry, galvanometry, and polarography; and 
 wherein the processor is further configured apply machine learning to determine a second characteristic of the mammal based on at least one of the determined characteristic of the biological waste and the first characteristic of the mammal, the machine learning applied via a machine learning model trained with the library data to recognize characteristics of the mammal relating to previously determined characteristics of biological waste and mammals. 
   
     
     
         45 . The system of  claim 44 , wherein the biological waste comprises at least one of: a solid, a liquid, a gas, and plasma. 
     
     
         46 . The system of  claim 44 , wherein the biological waste is undergoing a chemical reaction. 
     
     
         47 . The system of  claim 44 , wherein the biological waste is a bodily fluid of the mammal. 
     
     
         48 . The system of  claim 44 , wherein the mammal is a human, and the processor is further configured to determine a health characteristic of the human based on the characteristics of the mammal and the biological waste. 
     
     
         49 . The system of  claim 44 , wherein the processor is further configured to generate a meal planning recommendation to correct a nutritional health of the mammal based on the second characteristic. 
     
     
         50 . The system of  claim 44 , wherein the processor generates an alert representing the second characteristic. 
     
     
         51 . The system of  claim 44 , wherein the computing device is in communication with a wireless communications device and configured to transmit data representing the second characteristic to the wireless communications device. 
     
     
         52 . The device of  claim 16 , wherein the third machine learning algorithm is further configured to determine the second characteristic based on the stimulus and response signals. 
     
     
         53 . A non-transitory machine-readable medium of  claim 37 , further comprising instructions that when executed cause a processor to apply the third machine learning model to determine the health characteristic based on the stimulus and response signals.